wassname
67f3fd8409
arg for action scale
2018-01-21 12:46:07 +08:00
wassname
f4c45b03db
fix norm
2018-01-21 12:45:56 +08:00
wassname
11cb4d9cce
remove commented code
2018-01-21 12:45:21 +08:00
wassname
c4065bb7db
clean up nets and args
2018-01-21 12:35:29 +08:00
wassname
6bb9c51403
add share normalizer for state and reward
2018-01-21 12:35:13 +08:00
wassname
cd949644d3
bugfixes
2018-01-19 14:09:36 +08:00
wassname
8d9e2024c1
add debug arg
2018-01-19 14:09:23 +08:00
wassname
66d6a74093
add logger
2018-01-19 13:05:32 +08:00
wassname
adcafeada3
add debug, vs multithread
2018-01-19 12:08:49 +08:00
wassname
201fa2400f
add dynamics lr
2018-01-19 12:08:32 +08:00
wassname
a87a3ad7bb
tidy
2018-01-18 17:23:35 +08:00
wassname
d9b67e5f9a
change log dir
2018-01-18 16:50:15 +08:00
wassname
865b2a03b7
tidy typos
2018-01-18 16:50:04 +08:00
wassname
0de68133cf
ddpg with a dynamics model
...
I'm trying a dynamics model to provide additional supervision. I'm using
this repo because it's performance tested on a competition and is in
pytorch. I'm intially testing with pendulum. Code is messy as it's a one
time experiment.
2018-01-18 16:41:20 +08:00
Kolesnikov Sergey
814607dc94
more versions
2017-11-15 23:38:27 +03:00
Kolesnikov Sergey
8ba895eec1
typo :)
2017-11-15 22:21:19 +03:00
Kolesnikov Sergey
7401266fe7
pytorch version
2017-11-15 22:18:46 +03:00
Sergey Kolesnikov
34993abdf7
Initial commit
2017-11-15 21:04:29 +03:00